KLM wastes less food on board planes thanks to artificial intelligence. AI programs allow the company to better predict how many passengers, who have reserved in-flight menus, will actually board a flight. This allows the exact number of meals needed to be calculated, and KLM has been able to combat up to 63% less food waste based on the expected number of passengers per flight. On an annual basis, this means a saving of over 100.000 kg of food.
Investments in digital technology are a priority for KLM. The application of artificial intelligence contributes enormously to improving our flight operations and making them more sustainable. Fighting food waste is a good example of this, saving tens of thousands of meals on KLM flights.
Marjan Rintel, KLM CEO
KLM uses artificial intelligence to determine the number of meals on board to help combat food waste. The idea is that, depending on the class, between 3 and 5% of passengers who book plane tickets and meals do not show up (on time) for the flight.
The latest AI model (TRAYS) is the first developed specifically for KLM's catering activities. The AI model predicts the number of passengers on board based on historical data. The Meals On Board (MOBS) system receives the expected number of passengers per flight with separate forecasts for Business, Premium Comfort and Economy classes. Prediction using AI model starts 17 days before departure and continues 20 minutes before flight departure. This means that the most accurate number of passengers is provided for the entire catering process, from purchase to boarding, thus preventing a surplus of meals.
A three-month analysis shows that 63% less food is wasted compared to previous periods. The biggest improvement can be seen on KLM's intercontinental flights from Schiphol, where 2,5 fewer meals (1,3 kg) need to be thrown away per flight. On an annual basis, this means a saving of over 1000.000 kg in food for all KLM flights from Schiphol.